-
公开(公告)号：US20080240607A1
公开(公告)日：2008-10-02
申请号：US11961752
申请日：2007-12-20
申请人： Jian Sun , Heung-Yeung Shum
发明人： Jian Sun , Heung-Yeung Shum
IPC分类号： G06K9/40
摘要： Image deblurring with blurred/noisy image pairs is described. In one implementation, a system combines a blurred image with a corresponding noisy image of the same subject to create a high-quality deblurred image. The blurred/noisy image pair can be acquired by an inexpensive hand-held camera, e.g., in unfavorable low light conditions. An exemplary iterative process uses the blurred image and the noisy image at each step to produce the high-quality image. First, the system estimates the blur kernel of the blurred image using information from both the blurred and noisy images. Then, the system performs residual image deconvolution, which favors suppression of ringing artifacts. Finally, the system applies gain-controlled deconvolution to suppress remaining ringing artifacts in smooth image regions. The system iterates these steps to obtain the final high-quality image.
摘要翻译： 描述了具有模糊/噪声图像对的图像去模糊。 在一个实现中，系统将模糊图像与相同对象的对应噪声图像相结合，以创建高质量的去模糊图像。 模糊/嘈杂的图像对可以由便宜的手持相机获取，例如在不利的低光条件下。 示例性迭代过程在每个步骤使用模糊图像和噪声图像来产生高质量图像。 首先，系统使用来自模糊和嘈杂图像的信息来估计模糊图像的模糊内核。 然后，系统执行残差图像去卷积，有利于抑制振铃伪像。 最后，系统采用增益控制去卷积来抑制平滑图像区域中的剩余振铃伪像。 系统迭代这些步骤以获得最终的高质量图像。
-
公开(公告)号：US07317843B2
公开(公告)日：2008-01-08
申请号：US10817633
申请日：2004-04-01
申请人： Jian Sun , Jiaya Jia , Heung-Yeung Shum
发明人： Jian Sun , Jiaya Jia , Heung-Yeung Shum
CPC分类号： G06T5/40 , G06T5/009 , G06T5/50 , G06T2207/10024 , G06T2207/10144 , H04N5/217 , H04N5/23229 , H04N5/2355 , H04N5/35581
摘要： Techniques are disclosed to improve quality of images that may be blurred or underexposed. In one described implementation, a method includes providing two images of a same scene. The method determines a spatial coherence and color statistics of the two images. The determined color statistics and spatial coherence are utilized to enhance one of the two images.
摘要翻译： 公开了提高可能模糊或曝光不足的图像质量的技术。 在一个描述的实现中，一种方法包括提供相同场景的两个图像。 该方法确定两个图像的空间相干性和颜色统计。 使用确定的颜色统计和空间相干性来增强两个图像之一。
-
公开(公告)号：US20070122028A1
公开(公告)日：2007-05-31
申请号：US11289907
申请日：2005-11-30
申请人： Jian Sun , Yin Li , Sing Kang , Heung-Yeung Shum
发明人： Jian Sun , Yin Li , Sing Kang , Heung-Yeung Shum
IPC分类号： G06K9/00
CPC分类号： G06K9/32
摘要： The present symmetric stereo matching technique provides a method for iteratively estimating a minimum energy for occlusion and disparity using belief propagation. The minimum energy is based on an energy minimization framework in which a visibility constraint is embedded. By embedding the visibility constraint, the present symmetric stereo matching technique treats both images equally, instead of treating one as a reference image. The visibility constraint ensures that occlusion in one view and the disparity in another view are consistent.
摘要翻译： 本对称立体匹配技术提供了一种使用置信传播迭代估计遮挡和视差的最小能量的方法。 最小能量基于嵌入可见性约束的能量最小化框架。 通过嵌入可见度约束，本对称立体匹配技术可以平等对待两个图像，而不是将其视为参考图像。 可见性约束确保一个视图中的遮挡和另一个视图中的视差是一致的。
-
公开(公告)号：US20050220359A1
公开(公告)日：2005-10-06
申请号：US10817633
申请日：2004-04-01
申请人： Jian Sun , Jiaya Jia , Heung-Yeung Shum
发明人： Jian Sun , Jiaya Jia , Heung-Yeung Shum
IPC分类号： G06T1/00 , G06T5/00 , G06T5/40 , G06T5/50 , H04N1/407 , H04N1/46 , H04N1/60 , G06K9/00 , G06K9/40
CPC分类号： G06T5/40 , G06T5/009 , G06T5/50 , G06T2207/10024 , G06T2207/10144 , H04N5/217 , H04N5/23229 , H04N5/2355 , H04N5/35581
摘要： Techniques are disclosed to improve quality of images that may be blurred or underexposed. In one described implementation, a method includes providing two images of a same scene. The method determines a spatial coherence and color statistics of the two images. The determined color statistics and spatial coherence are utilized to enhance one of the two images.
摘要翻译： 公开了提高可能模糊或曝光不足的图像质量的技术。 在一个描述的实现中，一种方法包括提供相同场景的两个图像。 该方法确定两个图像的空间相干性和颜色统计。 使用确定的颜色统计和空间相干性来增强两个图像之一。
-
公开(公告)号：US08184926B2
公开(公告)日：2012-05-22
申请号：US11961752
申请日：2007-12-20
申请人： Jian Sun , Heung-Yeung Shum
发明人： Jian Sun , Heung-Yeung Shum
摘要： Image deblurring with blurred/noisy image pairs is described. In one implementation, a system combines a blurred image with a corresponding noisy image of the same subject to create a high-quality deblurred image. The blurred/noisy image pair can be acquired by an inexpensive hand-held camera, e.g., in unfavorable low light conditions. An exemplary iterative process uses the blurred image and the noisy image at each step to produce the high-quality image. First, the system estimates the blur kernel of the blurred image using information from both the blurred and noisy images. Then, the system performs residual image deconvolution, which favors suppression of ringing artifacts. Finally, the system applies gain-controlled deconvolution to suppress remaining ringing artifacts in smooth image regions. The system iterates these steps to obtain the final high-quality image.
摘要翻译： 描述了具有模糊/噪声图像对的图像去模糊。 在一个实现中，系统将模糊图像与相同对象的对应噪声图像相结合，以创建高质量的去模糊图像。 模糊/嘈杂的图像对可以由便宜的手持相机获取，例如在不利的低光条件下。 示例性迭代过程在每个步骤使用模糊图像和噪声图像来产生高质量图像。 首先，系统使用来自模糊和嘈杂图像的信息来估计模糊图像的模糊内核。 然后，系统执行残差图像去卷积，有利于抑制振铃伪像。 最后，系统采用增益控制去卷积来抑制平滑图像区域中的剩余振铃伪像。 系统迭代这些步骤以获得最终的高质量图像。
-
公开(公告)号：US07636128B2
公开(公告)日：2009-12-22
申请号：US11183226
申请日：2005-07-15
申请人： Jian Sun , Jiaya Jia , Heung-Yeung Shum
发明人： Jian Sun , Jiaya Jia , Heung-Yeung Shum
CPC分类号： G06T7/12 , G06T7/194 , G06T2207/20092
摘要： An exemplary method includes receiving a trimap for an image that specifies a background region, a foreground region and an unknown region for the image wherein a boundary exists between the foreground region and the unknown region and wherein another boundary exists between the unknown region and the background region, solving a set of Poisson equations having boundary conditions for the two boundaries to provide a matte that distinguishes a foreground region from a background region in the unknown region, and refining the matte by solving a set of Poisson equations for a local unknown region. Various other exemplary technologies are also presented.
摘要翻译： 一种示例性方法包括：接收用于图像的微调，该图像指定用于图像的背景区域，前景区域和未知区域，其中在前景区域和未知区域之间存在边界，并且其中在未知区域和背景之间存在另一边界 区域，求解一组具有两个边界的边界条件的泊松方程，以提供区分未知区域中的前景区域和背景区域的无光泽，以及通过求解一组局部未知区域的泊松方程来改善无光泽。 还提出了各种其它示例性技术。
-
公开(公告)号：US07609888B2
公开(公告)日：2009-10-27
申请号：US11173882
申请日：2005-07-01
申请人： Jian Sun , Heung-Yeung Shum , Yin Li
发明人： Jian Sun , Heung-Yeung Shum , Yin Li
IPC分类号： G06K9/34
CPC分类号： G06K9/00369 , G06T7/11 , G06T7/162 , G06T2207/10016 , G06T2207/10024 , G06T2207/20016 , G06T2207/20072 , G06T2207/20104 , G06T2207/20152
摘要： Video object cutting and pasting is described. In one implementation, pre-segmentation of video frames into regions is performed prior to a 3-D graph cut segmentation. The 3-D graph cut segmentation uses temporal coherence and a global color model to achieve accuracy of video object boundaries. A 2-D local graph cut segmentation can then be used to refine the boundaries. The boundaries can be tracked within a user-selected sequence of windows and refined using a local color model.
摘要翻译： 描述了视频对象切割和粘贴。 在一个实现中，在3D切割分割之前执行视频帧到区域的预分割。 3-D图形切割分割使用时间相干性和全局颜色模型来实现视频对象边界的准确性。 然后可以使用2-D局部图形切割分割来细化边界。 可以在用户选择的窗口序列内跟踪边界，并使用本地颜色模型进行细化。
-
公开(公告)号：US20080198175A1
公开(公告)日：2008-08-21
申请号：US11676806
申请日：2007-02-20
申请人： Jian Sun , Jiaya Jia , Heung-Yeung Shum
发明人： Jian Sun , Jiaya Jia , Heung-Yeung Shum
IPC分类号： G06T1/00
CPC分类号： H04N1/3876 , G06T7/12 , G06T7/162 , G06T7/194 , G06T11/60 , G06T2207/10024 , G06T2207/20096
摘要： Systems and methods provide drag-and-drop pasting for seamless image composition. In one implementation, a user casually outlines a region of a source image that contains a visual object to be pasted into a target image. An exemplary system automatically calculates a new boundary within this region, such that when pasted at this boundary, visual seams are minimized. The system applies a shortest path calculation to find the optimal pasting boundary. The best path has minimal color variation along its length, thus avoiding structure and visual objects in the target image and providing the best chance for seamlessness. Poisson image editing is applied across this optimized boundary to blend colors. When the visual object being pasted has fine structure at its border that could be truncated by the Poisson editing, the exemplary system integrates the alpha matte of the visual object into the Poisson equations to protect the fine structure.
摘要翻译： 系统和方法为无缝图像组合提供拖放粘贴。 在一个实现中，用户随意地概括了包含要粘贴到目标图像中的视觉对象的源图像的区域。 示例性系统自动计算该区域内的新边界，使得当粘贴在该边界处时，视觉接缝被最小化。 系统应用最短路径计算来找到最佳粘贴边界。 最佳路径沿其长度具有最小的颜色变化，从而避免了目标图像中的结构和视觉对象，并提供了无缝隙的最佳机会。 Poisson图像编辑应用于这个优化的边界以混合颜色。 当粘贴的视觉对象在其边界处具有可被泊松编辑截断的精细结构时，示例性系统将视觉对象的α无光泽整合到泊松方程中以保护精细结构。
-
公开(公告)号：US20070003154A1
公开(公告)日：2007-01-04
申请号：US11173882
申请日：2005-07-01
申请人： Jian Sun , Heung-Yeung Shum , Yin Li
发明人： Jian Sun , Heung-Yeung Shum , Yin Li
CPC分类号： G06K9/00369 , G06T7/11 , G06T7/162 , G06T2207/10016 , G06T2207/10024 , G06T2207/20016 , G06T2207/20072 , G06T2207/20104 , G06T2207/20152
摘要： Video object cutting and pasting is described. In one implementation, pre-segmentation of video frames into regions is performed prior to a 3-D graph cut segmentation. The 3-D graph cut segmentation uses temporal coherence and a global color model to achieve accuracy of video object boundaries. A 2-D local graph cut segmentation can then be used to refine the boundaries. The boundaries can be tracked within a user-selected sequence of windows and refined using a local color model.
摘要翻译： 描述了视频对象切割和粘贴。 在一个实现中，在3D切割分割之前执行视频帧到区域的预分割。 3-D图形切割分割使用时间相干性和全局颜色模型来实现视频对象边界的准确性。 然后可以使用2-D局部图形切割分割来细化边界。 可以在用户选择的窗口序列内跟踪边界，并使用本地颜色模型进行细化。
-
公开(公告)号：US20060029275A1
公开(公告)日：2006-02-09
申请号：US10912923
申请日：2004-08-06
申请人： Yin Li , Jian Sun , Chi Tang , Heung-Yeung Shum
发明人： Yin Li , Jian Sun , Chi Tang , Heung-Yeung Shum
摘要： A method includes receiving a first set of one or more data nodes specified by a user using a first specification mode, receiving a second set of one or more data nodes specified by a user using a second specification mode, and automatically identifying a data node to be separated from a collection of data nodes based on a similarity measure characterizing similarity between the data node to be separated and the one or more data nodes in the first set and the one or more data nodes in the second set. A system includes an image processing module automatically segmenting a determined region from an image based on a similarity measure characterizing similarity between pixels in the determined region and a set of one or more specified seed pixels associated with pixels to be included in the determined region.
摘要翻译： 一种方法包括：使用第一规范模式接收由用户指定的一个或多个数据节点的第一组，接收由用户使用第二规范模式指定的一个或多个数据节点的第二组，并自动识别数据节点 基于表示要分离的数据节点与第一组中的一个或多个数据节点和第二组中的一个或多个数据节点之间的相似性的相似性度量来从数据节点的集合中分离出来。 一种系统包括图像处理模块，该图像处理模块基于表征所确定区域中的像素之间的相似度的相似性度量和与要确定的区域中包括的像素相关联的一个或多个指定的种子像素的集合，自动地从图像中分割确定的区域。
-
-
-
-
-
-
-
-
-
搜索结果
163 条记录 (耗时 0.034 秒)
